llvm-project/llvm/lib/CodeGen/AsmPrinter/DwarfCompileUnit.cpp

879 lines
34 KiB
C++
Raw Normal View History

//===-- llvm/CodeGen/DwarfCompileUnit.cpp - Dwarf Compile Units -----------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file contains support for constructing a dwarf compile unit.
//
//===----------------------------------------------------------------------===//
#include "DwarfCompileUnit.h"
#include "DwarfExpression.h"
#include "llvm/CodeGen/MachineFunction.h"
AsmPrinter: Create a unified .debug_loc stream This commit removes `DebugLocList` and replaces it with `DebugLocStream`. - `DebugLocEntry` no longer contains its byte/comment streams. - The `DebugLocEntry` list for a variable/inlined-at pair is allocated on the stack, and released right after `DebugLocEntry::finalize()` (possible because of the refactoring in r231023). Now, only one list is in memory at a time now. - There's a single unified stream for the `.debug_loc` section that persists, stored in the new `DebugLocStream` data structure. The last point is important: this collapses the nested `SmallVector<>`s from `DebugLocList` into unified streams. We previously had something like the following: vec<tuple<Label, CU, vec<tuple<BeginSym, EndSym, vec<Value>, vec<char>, vec<string>>>>> A `SmallVector` can avoid allocations, but is statically fairly large for a vector: three pointers plus the size of the small storage, which is the number of elements in small mode times the element size). Nesting these is expensive, since an inner vector's size contributes to the element size of an outer one. (Nesting any vector is expensive...) In the old data structure, the outer vector's *element* size was 632B, excluding allocation costs for when the middle and inner vectors exceeded their small sizes. 312B of this was for the "three" pointers in the vector-tree beneath it. If you assume 1M functions with an average of 10 variable/inlined-at pairs each (in an LTO scenario), that's almost 6GB (besides inner allocations), with almost 3GB for the "three" pointers. This came up in a heap profile a little while ago of a `clang -flto -g` bootstrap, with `DwarfDebug::collectVariableInfo()` using something like 10-15% of the total memory. With this commit, we have: tuple<vec<tuple<Label, CU, Offset>>, vec<tuple<BeginSym, EndSym, Offset, Offset>>, vec<char>, vec<string>> The offsets are used to create `ArrayRef` slices of adjacent `SmallVector`s. This reduces the number of vectors to four (unrelated to the number of variable/inlined-at pairs), and caps the number of allocations at the same number. Besides saving memory and limiting allocations, this is NFC. I don't know my way around this code very well yet, but I wonder if we could go further: why stream to a side-table, instead of directly to the output stream? llvm-svn: 235229
2015-04-18 05:34:47 +08:00
#include "llvm/IR/Constants.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/GlobalValue.h"
#include "llvm/IR/GlobalVariable.h"
#include "llvm/IR/Instruction.h"
#include "llvm/MC/MCAsmInfo.h"
#include "llvm/MC/MCStreamer.h"
#include "llvm/Target/TargetFrameLowering.h"
#include "llvm/Target/TargetLoweringObjectFile.h"
#include "llvm/Target/TargetMachine.h"
#include "llvm/Target/TargetRegisterInfo.h"
#include "llvm/Target/TargetSubtargetInfo.h"
namespace llvm {
DwarfCompileUnit::DwarfCompileUnit(unsigned UID, const DICompileUnit *Node,
AsmPrinter *A, DwarfDebug *DW,
DwarfFile *DWU)
: DwarfUnit(dwarf::DW_TAG_compile_unit, Node, A, DW, DWU), UniqueID(UID),
Skeleton(nullptr), BaseAddress(nullptr) {
insertDIE(Node, &getUnitDie());
MacroLabelBegin = Asm->createTempSymbol("cu_macro_begin");
}
/// addLabelAddress - Add a dwarf label attribute data and value using
/// DW_FORM_addr or DW_FORM_GNU_addr_index.
///
void DwarfCompileUnit::addLabelAddress(DIE &Die, dwarf::Attribute Attribute,
const MCSymbol *Label) {
// Don't use the address pool in non-fission or in the skeleton unit itself.
// FIXME: Once GDB supports this, it's probably worthwhile using the address
// pool from the skeleton - maybe even in non-fission (possibly fewer
// relocations by sharing them in the pool, but we have other ideas about how
// to reduce the number of relocations as well/instead).
if (!DD->useSplitDwarf() || !Skeleton)
return addLocalLabelAddress(Die, Attribute, Label);
if (Label)
DD->addArangeLabel(SymbolCU(this, Label));
unsigned idx = DD->getAddressPool().getIndex(Label);
Die.addValue(DIEValueAllocator, Attribute, dwarf::DW_FORM_GNU_addr_index,
DIEInteger(idx));
}
void DwarfCompileUnit::addLocalLabelAddress(DIE &Die,
dwarf::Attribute Attribute,
const MCSymbol *Label) {
if (Label)
DD->addArangeLabel(SymbolCU(this, Label));
if (Label)
Die.addValue(DIEValueAllocator, Attribute, dwarf::DW_FORM_addr,
DIELabel(Label));
else
Die.addValue(DIEValueAllocator, Attribute, dwarf::DW_FORM_addr,
DIEInteger(0));
}
unsigned DwarfCompileUnit::getOrCreateSourceID(StringRef FileName,
StringRef DirName) {
// If we print assembly, we can't separate .file entries according to
// compile units. Thus all files will belong to the default compile unit.
// FIXME: add a better feature test than hasRawTextSupport. Even better,
// extend .file to support this.
return Asm->OutStreamer->EmitDwarfFileDirective(
0, DirName, FileName,
Asm->OutStreamer->hasRawTextSupport() ? 0 : getUniqueID());
}
DIE *DwarfCompileUnit::getOrCreateGlobalVariableDIE(
const DIGlobalVariable *GV, ArrayRef<GlobalExpr> GlobalExprs) {
// Check for pre-existence.
if (DIE *Die = getDIE(GV))
return Die;
assert(GV);
auto *GVContext = GV->getScope();
auto *GTy = DD->resolve(GV->getType());
// Construct the context before querying for the existence of the DIE in
// case such construction creates the DIE.
DIE *ContextDIE = getOrCreateContextDIE(GVContext);
// Add to map.
DIE *VariableDIE = &createAndAddDIE(GV->getTag(), *ContextDIE, GV);
DIScope *DeclContext;
if (auto *SDMDecl = GV->getStaticDataMemberDeclaration()) {
DeclContext = resolve(SDMDecl->getScope());
assert(SDMDecl->isStaticMember() && "Expected static member decl");
assert(GV->isDefinition());
// We need the declaration DIE that is in the static member's class.
DIE *VariableSpecDIE = getOrCreateStaticMemberDIE(SDMDecl);
addDIEEntry(*VariableDIE, dwarf::DW_AT_specification, *VariableSpecDIE);
// If the global variable's type is different from the one in the class
// member type, assume that it's more specific and also emit it.
if (GTy != DD->resolve(SDMDecl->getBaseType()))
addType(*VariableDIE, GTy);
} else {
DeclContext = GV->getScope();
// Add name and type.
addString(*VariableDIE, dwarf::DW_AT_name, GV->getDisplayName());
addType(*VariableDIE, GTy);
// Add scoping info.
if (!GV->isLocalToUnit())
addFlag(*VariableDIE, dwarf::DW_AT_external);
// Add line number info.
addSourceLine(*VariableDIE, GV);
}
if (!GV->isDefinition())
addFlag(*VariableDIE, dwarf::DW_AT_declaration);
else
addGlobalName(GV->getName(), *VariableDIE, DeclContext);
if (uint32_t AlignInBytes = GV->getAlignInBytes())
addUInt(*VariableDIE, dwarf::DW_AT_alignment, dwarf::DW_FORM_udata,
AlignInBytes);
// Add location.
bool addToAccelTable = false;
DIELoc *Loc = nullptr;
std::unique_ptr<DIEDwarfExpression> DwarfExpr;
for (const auto &GE : GlobalExprs) {
const GlobalVariable *Global = GE.Var;
const DIExpression *Expr = GE.Expr;
// For compatibility with DWARF 3 and earlier,
// DW_AT_location(DW_OP_constu, X, DW_OP_stack_value) becomes
// DW_AT_const_value(X).
if (GlobalExprs.size() == 1 && Expr && Expr->isConstant()) {
addToAccelTable = true;
addConstantValue(*VariableDIE, /*Unsigned=*/true, Expr->getElement(1));
break;
}
// We cannot describe the location of dllimport'd variables: the
// computation of their address requires loads from the IAT.
if (Global && Global->hasDLLImportStorageClass())
continue;
// Nothing to describe without address or constant.
if (!Global && (!Expr || !Expr->isConstant()))
continue;
if (!Loc) {
addToAccelTable = true;
Loc = new (DIEValueAllocator) DIELoc;
DwarfExpr = llvm::make_unique<DIEDwarfExpression>(*Asm, *this, *Loc);
}
if (Global) {
const MCSymbol *Sym = Asm->getSymbol(Global);
if (Global->isThreadLocal()) {
if (Asm->TM.Options.EmulatedTLS) {
// TODO: add debug info for emulated thread local mode.
} else {
// FIXME: Make this work with -gsplit-dwarf.
unsigned PointerSize = Asm->getDataLayout().getPointerSize();
assert((PointerSize == 4 || PointerSize == 8) &&
"Add support for other sizes if necessary");
// Based on GCC's support for TLS:
if (!DD->useSplitDwarf()) {
// 1) Start with a constNu of the appropriate pointer size
addUInt(*Loc, dwarf::DW_FORM_data1,
PointerSize == 4 ? dwarf::DW_OP_const4u
: dwarf::DW_OP_const8u);
// 2) containing the (relocated) offset of the TLS variable
// within the module's TLS block.
addExpr(*Loc, dwarf::DW_FORM_udata,
Asm->getObjFileLowering().getDebugThreadLocalSymbol(Sym));
} else {
addUInt(*Loc, dwarf::DW_FORM_data1, dwarf::DW_OP_GNU_const_index);
addUInt(*Loc, dwarf::DW_FORM_udata,
DD->getAddressPool().getIndex(Sym, /* TLS */ true));
}
// 3) followed by an OP to make the debugger do a TLS lookup.
addUInt(*Loc, dwarf::DW_FORM_data1,
DD->useGNUTLSOpcode() ? dwarf::DW_OP_GNU_push_tls_address
: dwarf::DW_OP_form_tls_address);
}
} else {
DD->addArangeLabel(SymbolCU(this, Sym));
addOpAddress(*Loc, Sym);
}
}
if (Expr) {
DwarfExpr->addFragmentOffset(Expr);
DwarfExpr->addExpression(Expr);
}
}
if (Loc)
addBlock(*VariableDIE, dwarf::DW_AT_location, DwarfExpr->finalize());
if (DD->useAllLinkageNames())
addLinkageName(*VariableDIE, GV->getLinkageName());
if (addToAccelTable) {
DD->addAccelName(GV->getName(), *VariableDIE);
// If the linkage name is different than the name, go ahead and output
// that as well into the name table.
if (GV->getLinkageName() != "" && GV->getName() != GV->getLinkageName())
DD->addAccelName(GV->getLinkageName(), *VariableDIE);
}
return VariableDIE;
}
void DwarfCompileUnit::addRange(RangeSpan Range) {
bool SameAsPrevCU = this == DD->getPrevCU();
DD->setPrevCU(this);
// If we have no current ranges just add the range and return, otherwise,
// check the current section and CU against the previous section and CU we
// emitted into and the subprogram was contained within. If these are the
// same then extend our current range, otherwise add this as a new range.
if (CURanges.empty() || !SameAsPrevCU ||
(&CURanges.back().getEnd()->getSection() !=
&Range.getEnd()->getSection())) {
CURanges.push_back(Range);
return;
}
CURanges.back().setEnd(Range.getEnd());
}
DIE::value_iterator
DwarfCompileUnit::addSectionLabel(DIE &Die, dwarf::Attribute Attribute,
const MCSymbol *Label, const MCSymbol *Sec) {
if (Asm->MAI->doesDwarfUseRelocationsAcrossSections())
return addLabel(Die, Attribute,
DD->getDwarfVersion() >= 4 ? dwarf::DW_FORM_sec_offset
: dwarf::DW_FORM_data4,
Label);
return addSectionDelta(Die, Attribute, Label, Sec);
}
void DwarfCompileUnit::initStmtList() {
// Define start line table label for each Compile Unit.
MCSymbol *LineTableStartSym =
Asm->OutStreamer->getDwarfLineTableSymbol(getUniqueID());
// DW_AT_stmt_list is a offset of line number information for this
// compile unit in debug_line section. For split dwarf this is
// left in the skeleton CU and so not included.
// The line table entries are not always emitted in assembly, so it
// is not okay to use line_table_start here.
const TargetLoweringObjectFile &TLOF = Asm->getObjFileLowering();
StmtListValue =
This change removes the dependency on DwarfDebug that was used for DW_FORM_ref_addr by making a new DIEUnit class in DIE.cpp. The DIEUnit class represents a compile or type unit and it owns the unit DIE as an instance variable. This allows anyone with a DIE, to get the unit DIE, and then get back to its DIEUnit without adding any new ivars to the DIE class. Why was this needed? The DIE class has an Offset that is always the CU relative DIE offset, not the "offset in debug info section" as was commented in the header file (the comment has been corrected). This is great for performance because most DIE references are compile unit relative and this means most code that accessed the DIE's offset didn't need to make it into a compile unit relative offset because it already was. When we needed to emit a DW_FORM_ref_addr though, we needed to find the absolute offset of the DIE by finding the DIE's compile/type unit. This class did have the absolute debug info/type offset and could be added to the CU relative offset to compute the absolute offset. With this change we can easily get back to a DIE's DIEUnit which will have this needed offset. Prior to this is required having a DwarfDebug and required calling: DwarfCompileUnit *DwarfDebug::lookupUnit(const DIE *CU) const; Now we can use the DIEUnit class to do so without needing DwarfDebug. All clients now use DIEUnit objects (the DwarfDebug stack and the DwarfLinker). A follow on patch for the DWARF generator will also take advantage of this. Differential Revision: https://reviews.llvm.org/D27170 llvm-svn: 288399
2016-12-02 02:56:29 +08:00
addSectionLabel(getUnitDie(), dwarf::DW_AT_stmt_list, LineTableStartSym,
TLOF.getDwarfLineSection()->getBeginSymbol());
}
void DwarfCompileUnit::applyStmtList(DIE &D) {
D.addValue(DIEValueAllocator, *StmtListValue);
}
void DwarfCompileUnit::attachLowHighPC(DIE &D, const MCSymbol *Begin,
const MCSymbol *End) {
assert(Begin && "Begin label should not be null!");
assert(End && "End label should not be null!");
assert(Begin->isDefined() && "Invalid starting label");
assert(End->isDefined() && "Invalid end label");
addLabelAddress(D, dwarf::DW_AT_low_pc, Begin);
if (DD->getDwarfVersion() < 4)
addLabelAddress(D, dwarf::DW_AT_high_pc, End);
else
addLabelDelta(D, dwarf::DW_AT_high_pc, End, Begin);
}
// Find DIE for the given subprogram and attach appropriate DW_AT_low_pc
// and DW_AT_high_pc attributes. If there are global variables in this
// scope then create and insert DIEs for these variables.
DIE &DwarfCompileUnit::updateSubprogramScopeDIE(const DISubprogram *SP) {
DIE *SPDie = getOrCreateSubprogramDIE(SP, includeMinimalInlineScopes());
attachLowHighPC(*SPDie, Asm->getFunctionBegin(), Asm->getFunctionEnd());
if (DD->useAppleExtensionAttributes() &&
!DD->getCurrentFunction()->getTarget().Options.DisableFramePointerElim(
*DD->getCurrentFunction()))
addFlag(*SPDie, dwarf::DW_AT_APPLE_omit_frame_ptr);
// Only include DW_AT_frame_base in full debug info
if (!includeMinimalInlineScopes()) {
const TargetRegisterInfo *RI = Asm->MF->getSubtarget().getRegisterInfo();
MachineLocation Location(RI->getFrameRegister(*Asm->MF));
if (RI->isPhysicalRegister(Location.getReg()))
addAddress(*SPDie, dwarf::DW_AT_frame_base, Location);
}
// Add name to the name table, we do this here because we're guaranteed
// to have concrete versions of our DW_TAG_subprogram nodes.
DD->addSubprogramNames(SP, *SPDie);
return *SPDie;
}
// Construct a DIE for this scope.
void DwarfCompileUnit::constructScopeDIE(
LexicalScope *Scope, SmallVectorImpl<DIE *> &FinalChildren) {
if (!Scope || !Scope->getScopeNode())
return;
auto *DS = Scope->getScopeNode();
assert((Scope->getInlinedAt() || !isa<DISubprogram>(DS)) &&
"Only handle inlined subprograms here, use "
"constructSubprogramScopeDIE for non-inlined "
"subprograms");
SmallVector<DIE *, 8> Children;
// We try to create the scope DIE first, then the children DIEs. This will
// avoid creating un-used children then removing them later when we find out
// the scope DIE is null.
DIE *ScopeDIE;
if (Scope->getParent() && isa<DISubprogram>(DS)) {
ScopeDIE = constructInlinedScopeDIE(Scope);
if (!ScopeDIE)
return;
// We create children when the scope DIE is not null.
createScopeChildrenDIE(Scope, Children);
} else {
// Early exit when we know the scope DIE is going to be null.
if (DD->isLexicalScopeDIENull(Scope))
return;
unsigned ChildScopeCount;
// We create children here when we know the scope DIE is not going to be
// null and the children will be added to the scope DIE.
createScopeChildrenDIE(Scope, Children, &ChildScopeCount);
// Skip imported directives in gmlt-like data.
if (!includeMinimalInlineScopes()) {
// There is no need to emit empty lexical block DIE.
for (const auto *IE : ImportedEntities[DS])
Children.push_back(
constructImportedEntityDIE(cast<DIImportedEntity>(IE)));
}
// If there are only other scopes as children, put them directly in the
// parent instead, as this scope would serve no purpose.
if (Children.size() == ChildScopeCount) {
FinalChildren.insert(FinalChildren.end(),
std::make_move_iterator(Children.begin()),
std::make_move_iterator(Children.end()));
return;
}
ScopeDIE = constructLexicalScopeDIE(Scope);
assert(ScopeDIE && "Scope DIE should not be null.");
}
// Add children
for (auto &I : Children)
ScopeDIE->addChild(std::move(I));
FinalChildren.push_back(std::move(ScopeDIE));
}
DIE::value_iterator
DwarfCompileUnit::addSectionDelta(DIE &Die, dwarf::Attribute Attribute,
const MCSymbol *Hi, const MCSymbol *Lo) {
return Die.addValue(DIEValueAllocator, Attribute,
DD->getDwarfVersion() >= 4 ? dwarf::DW_FORM_sec_offset
: dwarf::DW_FORM_data4,
new (DIEValueAllocator) DIEDelta(Hi, Lo));
}
void DwarfCompileUnit::addScopeRangeList(DIE &ScopeDIE,
SmallVector<RangeSpan, 2> Range) {
const TargetLoweringObjectFile &TLOF = Asm->getObjFileLowering();
// Emit offset in .debug_range as a relocatable label. emitDIE will handle
// emitting it appropriately.
const MCSymbol *RangeSectionSym =
TLOF.getDwarfRangesSection()->getBeginSymbol();
RangeSpanList List(Asm->createTempSymbol("debug_ranges"), std::move(Range));
// Under fission, ranges are specified by constant offsets relative to the
// CU's DW_AT_GNU_ranges_base.
if (isDwoUnit())
addSectionDelta(ScopeDIE, dwarf::DW_AT_ranges, List.getSym(),
RangeSectionSym);
else
addSectionLabel(ScopeDIE, dwarf::DW_AT_ranges, List.getSym(),
RangeSectionSym);
// Add the range list to the set of ranges to be emitted.
(Skeleton ? Skeleton : this)->CURangeLists.push_back(std::move(List));
}
void DwarfCompileUnit::attachRangesOrLowHighPC(
DIE &Die, SmallVector<RangeSpan, 2> Ranges) {
if (Ranges.size() == 1) {
const auto &single = Ranges.front();
attachLowHighPC(Die, single.getStart(), single.getEnd());
} else
addScopeRangeList(Die, std::move(Ranges));
}
void DwarfCompileUnit::attachRangesOrLowHighPC(
DIE &Die, const SmallVectorImpl<InsnRange> &Ranges) {
SmallVector<RangeSpan, 2> List;
List.reserve(Ranges.size());
for (const InsnRange &R : Ranges)
List.push_back(RangeSpan(DD->getLabelBeforeInsn(R.first),
DD->getLabelAfterInsn(R.second)));
attachRangesOrLowHighPC(Die, std::move(List));
}
// This scope represents inlined body of a function. Construct DIE to
// represent this concrete inlined copy of the function.
DIE *DwarfCompileUnit::constructInlinedScopeDIE(LexicalScope *Scope) {
assert(Scope->getScopeNode());
auto *DS = Scope->getScopeNode();
auto *InlinedSP = getDISubprogram(DS);
// Find the subprogram's DwarfCompileUnit in the SPMap in case the subprogram
// was inlined from another compile unit.
DIE *OriginDIE = DU->getAbstractSPDies()[InlinedSP];
assert(OriginDIE && "Unable to find original DIE for an inlined subprogram.");
auto ScopeDIE = DIE::get(DIEValueAllocator, dwarf::DW_TAG_inlined_subroutine);
addDIEEntry(*ScopeDIE, dwarf::DW_AT_abstract_origin, *OriginDIE);
attachRangesOrLowHighPC(*ScopeDIE, Scope->getRanges());
// Add the call site information to the DIE.
const DILocation *IA = Scope->getInlinedAt();
addUInt(*ScopeDIE, dwarf::DW_AT_call_file, None,
getOrCreateSourceID(IA->getFilename(), IA->getDirectory()));
addUInt(*ScopeDIE, dwarf::DW_AT_call_line, None, IA->getLine());
if (IA->getDiscriminator() && DD->getDwarfVersion() >= 4)
addUInt(*ScopeDIE, dwarf::DW_AT_GNU_discriminator, None,
IA->getDiscriminator());
// Add name to the name table, we do this here because we're guaranteed
// to have concrete versions of our DW_TAG_inlined_subprogram nodes.
DD->addSubprogramNames(InlinedSP, *ScopeDIE);
return ScopeDIE;
}
// Construct new DW_TAG_lexical_block for this scope and attach
// DW_AT_low_pc/DW_AT_high_pc labels.
DIE *DwarfCompileUnit::constructLexicalScopeDIE(LexicalScope *Scope) {
if (DD->isLexicalScopeDIENull(Scope))
return nullptr;
auto ScopeDIE = DIE::get(DIEValueAllocator, dwarf::DW_TAG_lexical_block);
if (Scope->isAbstractScope())
return ScopeDIE;
attachRangesOrLowHighPC(*ScopeDIE, Scope->getRanges());
return ScopeDIE;
}
/// constructVariableDIE - Construct a DIE for the given DbgVariable.
DIE *DwarfCompileUnit::constructVariableDIE(DbgVariable &DV, bool Abstract) {
auto D = constructVariableDIEImpl(DV, Abstract);
DV.setDIE(*D);
return D;
}
DIE *DwarfCompileUnit::constructVariableDIEImpl(const DbgVariable &DV,
bool Abstract) {
// Define variable debug information entry.
auto VariableDie = DIE::get(DIEValueAllocator, DV.getTag());
if (Abstract) {
applyVariableAttributes(DV, *VariableDie);
return VariableDie;
}
// Add variable address.
AsmPrinter: Create a unified .debug_loc stream This commit removes `DebugLocList` and replaces it with `DebugLocStream`. - `DebugLocEntry` no longer contains its byte/comment streams. - The `DebugLocEntry` list for a variable/inlined-at pair is allocated on the stack, and released right after `DebugLocEntry::finalize()` (possible because of the refactoring in r231023). Now, only one list is in memory at a time now. - There's a single unified stream for the `.debug_loc` section that persists, stored in the new `DebugLocStream` data structure. The last point is important: this collapses the nested `SmallVector<>`s from `DebugLocList` into unified streams. We previously had something like the following: vec<tuple<Label, CU, vec<tuple<BeginSym, EndSym, vec<Value>, vec<char>, vec<string>>>>> A `SmallVector` can avoid allocations, but is statically fairly large for a vector: three pointers plus the size of the small storage, which is the number of elements in small mode times the element size). Nesting these is expensive, since an inner vector's size contributes to the element size of an outer one. (Nesting any vector is expensive...) In the old data structure, the outer vector's *element* size was 632B, excluding allocation costs for when the middle and inner vectors exceeded their small sizes. 312B of this was for the "three" pointers in the vector-tree beneath it. If you assume 1M functions with an average of 10 variable/inlined-at pairs each (in an LTO scenario), that's almost 6GB (besides inner allocations), with almost 3GB for the "three" pointers. This came up in a heap profile a little while ago of a `clang -flto -g` bootstrap, with `DwarfDebug::collectVariableInfo()` using something like 10-15% of the total memory. With this commit, we have: tuple<vec<tuple<Label, CU, Offset>>, vec<tuple<BeginSym, EndSym, Offset, Offset>>, vec<char>, vec<string>> The offsets are used to create `ArrayRef` slices of adjacent `SmallVector`s. This reduces the number of vectors to four (unrelated to the number of variable/inlined-at pairs), and caps the number of allocations at the same number. Besides saving memory and limiting allocations, this is NFC. I don't know my way around this code very well yet, but I wonder if we could go further: why stream to a side-table, instead of directly to the output stream? llvm-svn: 235229
2015-04-18 05:34:47 +08:00
unsigned Offset = DV.getDebugLocListIndex();
if (Offset != ~0U) {
addLocationList(*VariableDie, dwarf::DW_AT_location, Offset);
return VariableDie;
}
// Check if variable is described by a DBG_VALUE instruction.
if (const MachineInstr *DVInsn = DV.getMInsn()) {
assert(DVInsn->getNumOperands() == 4);
if (DVInsn->getOperand(0).isReg()) {
const MachineOperand RegOp = DVInsn->getOperand(0);
// If the second operand is an immediate, this is an indirect value.
if (DVInsn->getOperand(1).isImm()) {
MachineLocation Location(RegOp.getReg(),
DVInsn->getOperand(1).getImm());
addVariableAddress(DV, *VariableDie, Location);
} else if (RegOp.getReg())
addVariableAddress(DV, *VariableDie, MachineLocation(RegOp.getReg()));
} else if (DVInsn->getOperand(0).isImm()) {
// This variable is described by a single constant.
// Check whether it has a DIExpression.
auto *Expr = DV.getSingleExpression();
if (Expr && Expr->getNumElements()) {
DIELoc *Loc = new (DIEValueAllocator) DIELoc;
DIEDwarfExpression DwarfExpr(*Asm, *this, *Loc);
// If there is an expression, emit raw unsigned bytes.
Fix LLVM's use of DW_OP_bit_piece in DWARF expressions. LLVM's use of DW_OP_bit_piece is incorrect and a based on a misunderstanding of the wording in the DWARF specification. The offset argument of DW_OP_bit_piece refers to the offset into the location that is on the top of the DWARF expression stack, and not an offset into the source variable. This has since also been clarified in the DWARF specification. This patch fixes all uses of DW_OP_bit_piece to emit the correct offset and simplifies the DwarfExpression class to semi-automaticaly emit empty DW_OP_pieces to adjust the offset of the source variable, thus simplifying the code using DwarfExpression. While this is an incompatible bugfix, in practice I don't expect this to be much of a problem since LLVM's old interpretation and the correct interpretation of DW_OP_bit_piece differ only when there are gaps in the fragmented locations of the described variables or if individual fragments are smaller than a byte. LLDB at least won't interpret locations with gaps in them because is has no way to present undefined bits in a variable, and there is a high probability that an old-form expression will be malformed when interpreted correctly, because the DW_OP_bit_piece offset will be outside of the location at the top of the stack. As a nice side-effect, this patch enables us to use a more efficient encoding for subregisters: In order to express a sub-register at a non-zero offset we now use a DW_OP_bit_piece instead of shifting the value into place manually. This patch also adds missing test coverage for code paths that weren't exercised before. <rdar://problem/29335809> Differential Revision: https://reviews.llvm.org/D27550 llvm-svn: 289266
2016-12-10 04:43:40 +08:00
DwarfExpr.addFragmentOffset(Expr);
DwarfExpr.addUnsignedConstant(DVInsn->getOperand(0).getImm());
DwarfExpr.addExpression(Expr);
addBlock(*VariableDie, dwarf::DW_AT_location, DwarfExpr.finalize());
} else
addConstantValue(*VariableDie, DVInsn->getOperand(0), DV.getType());
} else if (DVInsn->getOperand(0).isFPImm())
addConstantFPValue(*VariableDie, DVInsn->getOperand(0));
else if (DVInsn->getOperand(0).isCImm())
addConstantValue(*VariableDie, DVInsn->getOperand(0).getCImm(),
DV.getType());
return VariableDie;
}
// .. else use frame index.
if (!DV.hasFrameIndexExprs())
return VariableDie;
Reapply "AsmPrinter: Change DIEValue to be stored by value" This reverts commit r238350, effectively reapplying r238349 after fixing (all?) the problems, all somehow related to how I was using `AlignedArrayCharUnion<>` inside `DIEValue`: - MSVC can only handle `sizeof()` on types, not values. Change the assert. - GCC doesn't know the `is_trivially_copyable` type trait. Instead of asserting it, add destructors. - Call placement new even when constructing POD (i.e., the pointers). - Instead of copying the char buffer, copy the casted classes. I've left in a couple of `static_assert`s that I think both MSVC and GCC know how to handle. If the bots disagree with me, I'll remove them. - Check that the constructed type is either standard layout or a pointer. This protects against a programming error: we really want the "small" `DIEValue`s to be small and simple, so don't accidentally change them not to be. - Similarly, check that the size of the buffer is no bigger than a `uint64_t` or a pointer. (I thought checking against `sizeof(uint64_t)` would be good enough, but Chandler suggested that pointers might sometimes be bigger than that in the context of sanitizers.) I've also committed r238359 in the meantime, which introduces a DIEValue.def to simplify dispatching between the various types (thanks to a review comment by David Blaikie). Without that, this commit would be almost unintelligible. Here's the original commit message: -- Change `DIEValue` to be stored/passed/etc. by value, instead of reference. It's now a discriminated union, with a `Val` field storing the actual type. The classes that used to inherit from `DIEValue` no longer do. There are two categories of these: - Small values fit in a single pointer and are stored by value. - Large values require auxiliary storage, and are stored by reference. The only non-mechanical change is to tools/dsymutil/DwarfLinker.cpp. It was relying on `DIEInteger`s being passed around by reference, so I replaced that assumption with a `PatchLocation` type that stores a safe reference to where the `DIEInteger` lives instead. This commit causes a temporary regression in memory usage, since I've left merging `DIEAbbrevData` into `DIEValue` for a follow-up commit. I measured an increase from 845 MB to 879 MB, around 3.9%. The follow-up drops it lower than the starting point, and I've only recently brought the memory this low anyway, so I'm committing these changes separately to keep them incremental. (I also considered swapping the commits, but the other one first would cause a lot more code churn.) (I'm looking at `llc` memory usage on `verify-uselistorder.lto.opt.bc`; see r236629 for details.) -- llvm-svn: 238362
2015-05-28 06:14:58 +08:00
DIELoc *Loc = new (DIEValueAllocator) DIELoc;
DIEDwarfExpression DwarfExpr(*Asm, *this, *Loc);
for (auto &Fragment : DV.getFrameIndexExprs()) {
unsigned FrameReg = 0;
PR32382: Fix emitting complex DWARF expressions. The DWARF specification knows 3 kinds of non-empty simple location descriptions: 1. Register location descriptions - describe a variable in a register - consist of only a DW_OP_reg 2. Memory location descriptions - describe the address of a variable 3. Implicit location descriptions - describe the value of a variable - end with DW_OP_stack_value & friends The existing DwarfExpression code is pretty much ignorant of these restrictions. This used to not matter because we only emitted very short expressions that we happened to get right by accident. This patch makes DwarfExpression aware of the rules defined by the DWARF standard and now chooses the right kind of location description for each expression being emitted. This would have been an NFC commit (for the existing testsuite) if not for the way that clang describes captured block variables. Based on how the previous code in LLVM emitted locations, DW_OP_deref operations that should have come at the end of the expression are put at its beginning. Fixing this means changing the semantics of DIExpression, so this patch bumps the version number of DIExpression and implements a bitcode upgrade. There are two major changes in this patch: I had to fix the semantics of dbg.declare for describing function arguments. After this patch a dbg.declare always takes the *address* of a variable as the first argument, even if the argument is not an alloca. When lowering a DBG_VALUE, the decision of whether to emit a register location description or a memory location description depends on the MachineLocation — register machine locations may get promoted to memory locations based on their DIExpression. (Future) optimization passes that want to salvage implicit debug location for variables may do so by appending a DW_OP_stack_value. For example: DBG_VALUE, [RBP-8] --> DW_OP_fbreg -8 DBG_VALUE, RAX --> DW_OP_reg0 +0 DBG_VALUE, RAX, DIExpression(DW_OP_deref) --> DW_OP_reg0 +0 All testcases that were modified were regenerated from clang. I also added source-based testcases for each of these to the debuginfo-tests repository over the last week to make sure that no synchronized bugs slip in. The debuginfo-tests compile from source and run the debugger. https://bugs.llvm.org/show_bug.cgi?id=32382 <rdar://problem/31205000> Differential Revision: https://reviews.llvm.org/D31439 llvm-svn: 300522
2017-04-18 09:21:53 +08:00
const DIExpression *Expr = Fragment.Expr;
const TargetFrameLowering *TFI = Asm->MF->getSubtarget().getFrameLowering();
int Offset = TFI->getFrameIndexReference(*Asm->MF, Fragment.FI, FrameReg);
PR32382: Fix emitting complex DWARF expressions. The DWARF specification knows 3 kinds of non-empty simple location descriptions: 1. Register location descriptions - describe a variable in a register - consist of only a DW_OP_reg 2. Memory location descriptions - describe the address of a variable 3. Implicit location descriptions - describe the value of a variable - end with DW_OP_stack_value & friends The existing DwarfExpression code is pretty much ignorant of these restrictions. This used to not matter because we only emitted very short expressions that we happened to get right by accident. This patch makes DwarfExpression aware of the rules defined by the DWARF standard and now chooses the right kind of location description for each expression being emitted. This would have been an NFC commit (for the existing testsuite) if not for the way that clang describes captured block variables. Based on how the previous code in LLVM emitted locations, DW_OP_deref operations that should have come at the end of the expression are put at its beginning. Fixing this means changing the semantics of DIExpression, so this patch bumps the version number of DIExpression and implements a bitcode upgrade. There are two major changes in this patch: I had to fix the semantics of dbg.declare for describing function arguments. After this patch a dbg.declare always takes the *address* of a variable as the first argument, even if the argument is not an alloca. When lowering a DBG_VALUE, the decision of whether to emit a register location description or a memory location description depends on the MachineLocation — register machine locations may get promoted to memory locations based on their DIExpression. (Future) optimization passes that want to salvage implicit debug location for variables may do so by appending a DW_OP_stack_value. For example: DBG_VALUE, [RBP-8] --> DW_OP_fbreg -8 DBG_VALUE, RAX --> DW_OP_reg0 +0 DBG_VALUE, RAX, DIExpression(DW_OP_deref) --> DW_OP_reg0 +0 All testcases that were modified were regenerated from clang. I also added source-based testcases for each of these to the debuginfo-tests repository over the last week to make sure that no synchronized bugs slip in. The debuginfo-tests compile from source and run the debugger. https://bugs.llvm.org/show_bug.cgi?id=32382 <rdar://problem/31205000> Differential Revision: https://reviews.llvm.org/D31439 llvm-svn: 300522
2017-04-18 09:21:53 +08:00
DwarfExpr.addFragmentOffset(Expr);
SmallVector<uint64_t, 8> Ops;
Ops.push_back(dwarf::DW_OP_plus);
Ops.push_back(Offset);
PR32382: Fix emitting complex DWARF expressions. The DWARF specification knows 3 kinds of non-empty simple location descriptions: 1. Register location descriptions - describe a variable in a register - consist of only a DW_OP_reg 2. Memory location descriptions - describe the address of a variable 3. Implicit location descriptions - describe the value of a variable - end with DW_OP_stack_value & friends The existing DwarfExpression code is pretty much ignorant of these restrictions. This used to not matter because we only emitted very short expressions that we happened to get right by accident. This patch makes DwarfExpression aware of the rules defined by the DWARF standard and now chooses the right kind of location description for each expression being emitted. This would have been an NFC commit (for the existing testsuite) if not for the way that clang describes captured block variables. Based on how the previous code in LLVM emitted locations, DW_OP_deref operations that should have come at the end of the expression are put at its beginning. Fixing this means changing the semantics of DIExpression, so this patch bumps the version number of DIExpression and implements a bitcode upgrade. There are two major changes in this patch: I had to fix the semantics of dbg.declare for describing function arguments. After this patch a dbg.declare always takes the *address* of a variable as the first argument, even if the argument is not an alloca. When lowering a DBG_VALUE, the decision of whether to emit a register location description or a memory location description depends on the MachineLocation — register machine locations may get promoted to memory locations based on their DIExpression. (Future) optimization passes that want to salvage implicit debug location for variables may do so by appending a DW_OP_stack_value. For example: DBG_VALUE, [RBP-8] --> DW_OP_fbreg -8 DBG_VALUE, RAX --> DW_OP_reg0 +0 DBG_VALUE, RAX, DIExpression(DW_OP_deref) --> DW_OP_reg0 +0 All testcases that were modified were regenerated from clang. I also added source-based testcases for each of these to the debuginfo-tests repository over the last week to make sure that no synchronized bugs slip in. The debuginfo-tests compile from source and run the debugger. https://bugs.llvm.org/show_bug.cgi?id=32382 <rdar://problem/31205000> Differential Revision: https://reviews.llvm.org/D31439 llvm-svn: 300522
2017-04-18 09:21:53 +08:00
Ops.append(Expr->elements_begin(), Expr->elements_end());
DIExpressionCursor Cursor(Ops);
DwarfExpr.setMemoryLocationKind();
DwarfExpr.addMachineRegExpression(
*Asm->MF->getSubtarget().getRegisterInfo(), Cursor, FrameReg);
PR32382: Fix emitting complex DWARF expressions. The DWARF specification knows 3 kinds of non-empty simple location descriptions: 1. Register location descriptions - describe a variable in a register - consist of only a DW_OP_reg 2. Memory location descriptions - describe the address of a variable 3. Implicit location descriptions - describe the value of a variable - end with DW_OP_stack_value & friends The existing DwarfExpression code is pretty much ignorant of these restrictions. This used to not matter because we only emitted very short expressions that we happened to get right by accident. This patch makes DwarfExpression aware of the rules defined by the DWARF standard and now chooses the right kind of location description for each expression being emitted. This would have been an NFC commit (for the existing testsuite) if not for the way that clang describes captured block variables. Based on how the previous code in LLVM emitted locations, DW_OP_deref operations that should have come at the end of the expression are put at its beginning. Fixing this means changing the semantics of DIExpression, so this patch bumps the version number of DIExpression and implements a bitcode upgrade. There are two major changes in this patch: I had to fix the semantics of dbg.declare for describing function arguments. After this patch a dbg.declare always takes the *address* of a variable as the first argument, even if the argument is not an alloca. When lowering a DBG_VALUE, the decision of whether to emit a register location description or a memory location description depends on the MachineLocation — register machine locations may get promoted to memory locations based on their DIExpression. (Future) optimization passes that want to salvage implicit debug location for variables may do so by appending a DW_OP_stack_value. For example: DBG_VALUE, [RBP-8] --> DW_OP_fbreg -8 DBG_VALUE, RAX --> DW_OP_reg0 +0 DBG_VALUE, RAX, DIExpression(DW_OP_deref) --> DW_OP_reg0 +0 All testcases that were modified were regenerated from clang. I also added source-based testcases for each of these to the debuginfo-tests repository over the last week to make sure that no synchronized bugs slip in. The debuginfo-tests compile from source and run the debugger. https://bugs.llvm.org/show_bug.cgi?id=32382 <rdar://problem/31205000> Differential Revision: https://reviews.llvm.org/D31439 llvm-svn: 300522
2017-04-18 09:21:53 +08:00
DwarfExpr.addExpression(std::move(Cursor));
}
addBlock(*VariableDie, dwarf::DW_AT_location, DwarfExpr.finalize());
return VariableDie;
}
DIE *DwarfCompileUnit::constructVariableDIE(DbgVariable &DV,
const LexicalScope &Scope,
DIE *&ObjectPointer) {
auto Var = constructVariableDIE(DV, Scope.isAbstractScope());
if (DV.isObjectPointer())
ObjectPointer = Var;
return Var;
}
DIE *DwarfCompileUnit::createScopeChildrenDIE(LexicalScope *Scope,
SmallVectorImpl<DIE *> &Children,
unsigned *ChildScopeCount) {
DIE *ObjectPointer = nullptr;
for (DbgVariable *DV : DU->getScopeVariables().lookup(Scope))
Children.push_back(constructVariableDIE(*DV, *Scope, ObjectPointer));
unsigned ChildCountWithoutScopes = Children.size();
for (LexicalScope *LS : Scope->getChildren())
constructScopeDIE(LS, Children);
if (ChildScopeCount)
*ChildScopeCount = Children.size() - ChildCountWithoutScopes;
return ObjectPointer;
}
void DwarfCompileUnit::constructSubprogramScopeDIE(const DISubprogram *Sub, LexicalScope *Scope) {
DIE &ScopeDIE = updateSubprogramScopeDIE(Sub);
if (Scope) {
assert(!Scope->getInlinedAt());
assert(!Scope->isAbstractScope());
// Collect lexical scope children first.
// ObjectPointer might be a local (non-argument) local variable if it's a
// block's synthetic this pointer.
if (DIE *ObjectPointer = createAndAddScopeChildren(Scope, ScopeDIE))
addDIEEntry(ScopeDIE, dwarf::DW_AT_object_pointer, *ObjectPointer);
}
// If this is a variadic function, add an unspecified parameter.
DITypeRefArray FnArgs = Sub->getType()->getTypeArray();
// If we have a single element of null, it is a function that returns void.
// If we have more than one elements and the last one is null, it is a
// variadic function.
if (FnArgs.size() > 1 && !FnArgs[FnArgs.size() - 1] &&
!includeMinimalInlineScopes())
ScopeDIE.addChild(
DIE::get(DIEValueAllocator, dwarf::DW_TAG_unspecified_parameters));
}
DIE *DwarfCompileUnit::createAndAddScopeChildren(LexicalScope *Scope,
DIE &ScopeDIE) {
// We create children when the scope DIE is not null.
SmallVector<DIE *, 8> Children;
DIE *ObjectPointer = createScopeChildrenDIE(Scope, Children);
// Add children
for (auto &I : Children)
ScopeDIE.addChild(std::move(I));
return ObjectPointer;
}
void DwarfCompileUnit::constructAbstractSubprogramScopeDIE(
LexicalScope *Scope) {
DIE *&AbsDef = DU->getAbstractSPDies()[Scope->getScopeNode()];
if (AbsDef)
return;
auto *SP = cast<DISubprogram>(Scope->getScopeNode());
DIE *ContextDIE;
if (includeMinimalInlineScopes())
ContextDIE = &getUnitDie();
// Some of this is duplicated from DwarfUnit::getOrCreateSubprogramDIE, with
// the important distinction that the debug node is not associated with the
// DIE (since the debug node will be associated with the concrete DIE, if
// any). It could be refactored to some common utility function.
else if (auto *SPDecl = SP->getDeclaration()) {
ContextDIE = &getUnitDie();
getOrCreateSubprogramDIE(SPDecl);
} else
ContextDIE = getOrCreateContextDIE(resolve(SP->getScope()));
// Passing null as the associated node because the abstract definition
// shouldn't be found by lookup.
AbsDef = &createAndAddDIE(dwarf::DW_TAG_subprogram, *ContextDIE, nullptr);
applySubprogramAttributesToDefinition(SP, *AbsDef);
if (!includeMinimalInlineScopes())
addUInt(*AbsDef, dwarf::DW_AT_inline, None, dwarf::DW_INL_inlined);
if (DIE *ObjectPointer = createAndAddScopeChildren(Scope, *AbsDef))
addDIEEntry(*AbsDef, dwarf::DW_AT_object_pointer, *ObjectPointer);
}
DIE *DwarfCompileUnit::constructImportedEntityDIE(
const DIImportedEntity *Module) {
DIE *IMDie = DIE::get(DIEValueAllocator, (dwarf::Tag)Module->getTag());
insertDIE(Module, IMDie);
DIE *EntityDie;
auto *Entity = resolve(Module->getEntity());
if (auto *NS = dyn_cast<DINamespace>(Entity))
EntityDie = getOrCreateNameSpace(NS);
else if (auto *M = dyn_cast<DIModule>(Entity))
EntityDie = getOrCreateModule(M);
else if (auto *SP = dyn_cast<DISubprogram>(Entity))
EntityDie = getOrCreateSubprogramDIE(SP);
else if (auto *T = dyn_cast<DIType>(Entity))
EntityDie = getOrCreateTypeDIE(T);
else if (auto *GV = dyn_cast<DIGlobalVariable>(Entity))
EntityDie = getOrCreateGlobalVariableDIE(GV, {});
else
EntityDie = getDIE(Entity);
assert(EntityDie);
addSourceLine(*IMDie, Module->getLine(), Module->getScope()->getFilename(),
Module->getScope()->getDirectory());
addDIEEntry(*IMDie, dwarf::DW_AT_import, *EntityDie);
StringRef Name = Module->getName();
if (!Name.empty())
addString(*IMDie, dwarf::DW_AT_name, Name);
return IMDie;
}
void DwarfCompileUnit::finishSubprogramDefinition(const DISubprogram *SP) {
DIE *D = getDIE(SP);
if (DIE *AbsSPDIE = DU->getAbstractSPDies().lookup(SP)) {
if (D)
// If this subprogram has an abstract definition, reference that
addDIEEntry(*D, dwarf::DW_AT_abstract_origin, *AbsSPDIE);
} else {
assert(D || includeMinimalInlineScopes());
if (D)
// And attach the attributes
applySubprogramAttributesToDefinition(SP, *D);
}
}
void DwarfCompileUnit::emitHeader(bool UseOffsets) {
// Don't bother labeling the .dwo unit, as its offset isn't used.
if (!Skeleton) {
LabelBegin = Asm->createTempSymbol("cu_begin");
Asm->OutStreamer->EmitLabel(LabelBegin);
}
dwarf::UnitType UT = Skeleton ? dwarf::DW_UT_split_compile
: DD->useSplitDwarf() ? dwarf::DW_UT_skeleton
: dwarf::DW_UT_compile;
DwarfUnit::emitCommonHeader(UseOffsets, UT);
}
/// addGlobalName - Add a new global name to the compile unit.
void DwarfCompileUnit::addGlobalName(StringRef Name, const DIE &Die,
const DIScope *Context) {
if (includeMinimalInlineScopes())
return;
std::string FullName = getParentContextString(Context) + Name.str();
GlobalNames[FullName] = &Die;
}
void DwarfCompileUnit::addGlobalNameForTypeUnit(StringRef Name,
const DIScope *Context) {
if (includeMinimalInlineScopes())
return;
std::string FullName = getParentContextString(Context) + Name.str();
// Insert, allowing the entry to remain as-is if it's already present
// This way the CU-level type DIE is preferred over the "can't describe this
// type as a unit offset because it's not really in the CU at all, it's only
// in a type unit"
GlobalNames.insert(std::make_pair(std::move(FullName), &getUnitDie()));
}
/// Add a new global type to the unit.
void DwarfCompileUnit::addGlobalType(const DIType *Ty, const DIE &Die,
const DIScope *Context) {
if (includeMinimalInlineScopes())
return;
std::string FullName = getParentContextString(Context) + Ty->getName().str();
GlobalTypes[FullName] = &Die;
}
void DwarfCompileUnit::addGlobalTypeUnitType(const DIType *Ty,
const DIScope *Context) {
if (includeMinimalInlineScopes())
return;
std::string FullName = getParentContextString(Context) + Ty->getName().str();
// Insert, allowing the entry to remain as-is if it's already present
// This way the CU-level type DIE is preferred over the "can't describe this
// type as a unit offset because it's not really in the CU at all, it's only
// in a type unit"
GlobalTypes.insert(std::make_pair(std::move(FullName), &getUnitDie()));
}
/// addVariableAddress - Add DW_AT_location attribute for a
/// DbgVariable based on provided MachineLocation.
void DwarfCompileUnit::addVariableAddress(const DbgVariable &DV, DIE &Die,
MachineLocation Location) {
if (DV.hasComplexAddress())
addComplexAddress(DV, Die, dwarf::DW_AT_location, Location);
else if (DV.isBlockByrefVariable())
addBlockByrefAddress(DV, Die, dwarf::DW_AT_location, Location);
else
addAddress(Die, dwarf::DW_AT_location, Location);
}
/// Add an address attribute to a die based on the location provided.
void DwarfCompileUnit::addAddress(DIE &Die, dwarf::Attribute Attribute,
const MachineLocation &Location) {
Reapply "AsmPrinter: Change DIEValue to be stored by value" This reverts commit r238350, effectively reapplying r238349 after fixing (all?) the problems, all somehow related to how I was using `AlignedArrayCharUnion<>` inside `DIEValue`: - MSVC can only handle `sizeof()` on types, not values. Change the assert. - GCC doesn't know the `is_trivially_copyable` type trait. Instead of asserting it, add destructors. - Call placement new even when constructing POD (i.e., the pointers). - Instead of copying the char buffer, copy the casted classes. I've left in a couple of `static_assert`s that I think both MSVC and GCC know how to handle. If the bots disagree with me, I'll remove them. - Check that the constructed type is either standard layout or a pointer. This protects against a programming error: we really want the "small" `DIEValue`s to be small and simple, so don't accidentally change them not to be. - Similarly, check that the size of the buffer is no bigger than a `uint64_t` or a pointer. (I thought checking against `sizeof(uint64_t)` would be good enough, but Chandler suggested that pointers might sometimes be bigger than that in the context of sanitizers.) I've also committed r238359 in the meantime, which introduces a DIEValue.def to simplify dispatching between the various types (thanks to a review comment by David Blaikie). Without that, this commit would be almost unintelligible. Here's the original commit message: -- Change `DIEValue` to be stored/passed/etc. by value, instead of reference. It's now a discriminated union, with a `Val` field storing the actual type. The classes that used to inherit from `DIEValue` no longer do. There are two categories of these: - Small values fit in a single pointer and are stored by value. - Large values require auxiliary storage, and are stored by reference. The only non-mechanical change is to tools/dsymutil/DwarfLinker.cpp. It was relying on `DIEInteger`s being passed around by reference, so I replaced that assumption with a `PatchLocation` type that stores a safe reference to where the `DIEInteger` lives instead. This commit causes a temporary regression in memory usage, since I've left merging `DIEAbbrevData` into `DIEValue` for a follow-up commit. I measured an increase from 845 MB to 879 MB, around 3.9%. The follow-up drops it lower than the starting point, and I've only recently brought the memory this low anyway, so I'm committing these changes separately to keep them incremental. (I also considered swapping the commits, but the other one first would cause a lot more code churn.) (I'm looking at `llc` memory usage on `verify-uselistorder.lto.opt.bc`; see r236629 for details.) -- llvm-svn: 238362
2015-05-28 06:14:58 +08:00
DIELoc *Loc = new (DIEValueAllocator) DIELoc;
DIEDwarfExpression DwarfExpr(*Asm, *this, *Loc);
if (Location.isIndirect())
DwarfExpr.setMemoryLocationKind();
SmallVector<uint64_t, 8> Ops;
PR32382: Fix emitting complex DWARF expressions. The DWARF specification knows 3 kinds of non-empty simple location descriptions: 1. Register location descriptions - describe a variable in a register - consist of only a DW_OP_reg 2. Memory location descriptions - describe the address of a variable 3. Implicit location descriptions - describe the value of a variable - end with DW_OP_stack_value & friends The existing DwarfExpression code is pretty much ignorant of these restrictions. This used to not matter because we only emitted very short expressions that we happened to get right by accident. This patch makes DwarfExpression aware of the rules defined by the DWARF standard and now chooses the right kind of location description for each expression being emitted. This would have been an NFC commit (for the existing testsuite) if not for the way that clang describes captured block variables. Based on how the previous code in LLVM emitted locations, DW_OP_deref operations that should have come at the end of the expression are put at its beginning. Fixing this means changing the semantics of DIExpression, so this patch bumps the version number of DIExpression and implements a bitcode upgrade. There are two major changes in this patch: I had to fix the semantics of dbg.declare for describing function arguments. After this patch a dbg.declare always takes the *address* of a variable as the first argument, even if the argument is not an alloca. When lowering a DBG_VALUE, the decision of whether to emit a register location description or a memory location description depends on the MachineLocation — register machine locations may get promoted to memory locations based on their DIExpression. (Future) optimization passes that want to salvage implicit debug location for variables may do so by appending a DW_OP_stack_value. For example: DBG_VALUE, [RBP-8] --> DW_OP_fbreg -8 DBG_VALUE, RAX --> DW_OP_reg0 +0 DBG_VALUE, RAX, DIExpression(DW_OP_deref) --> DW_OP_reg0 +0 All testcases that were modified were regenerated from clang. I also added source-based testcases for each of these to the debuginfo-tests repository over the last week to make sure that no synchronized bugs slip in. The debuginfo-tests compile from source and run the debugger. https://bugs.llvm.org/show_bug.cgi?id=32382 <rdar://problem/31205000> Differential Revision: https://reviews.llvm.org/D31439 llvm-svn: 300522
2017-04-18 09:21:53 +08:00
if (Location.isIndirect() && Location.getOffset()) {
Ops.push_back(dwarf::DW_OP_plus);
Ops.push_back(Location.getOffset());
}
DIExpressionCursor Cursor(Ops);
const TargetRegisterInfo &TRI = *Asm->MF->getSubtarget().getRegisterInfo();
if (!DwarfExpr.addMachineRegExpression(TRI, Cursor, Location.getReg()))
return;
DwarfExpr.addExpression(std::move(Cursor));
// Now attach the location information to the DIE.
addBlock(Die, Attribute, DwarfExpr.finalize());
}
/// Start with the address based on the location provided, and generate the
/// DWARF information necessary to find the actual variable given the extra
/// address information encoded in the DbgVariable, starting from the starting
/// location. Add the DWARF information to the die.
void DwarfCompileUnit::addComplexAddress(const DbgVariable &DV, DIE &Die,
dwarf::Attribute Attribute,
const MachineLocation &Location) {
Reapply "AsmPrinter: Change DIEValue to be stored by value" This reverts commit r238350, effectively reapplying r238349 after fixing (all?) the problems, all somehow related to how I was using `AlignedArrayCharUnion<>` inside `DIEValue`: - MSVC can only handle `sizeof()` on types, not values. Change the assert. - GCC doesn't know the `is_trivially_copyable` type trait. Instead of asserting it, add destructors. - Call placement new even when constructing POD (i.e., the pointers). - Instead of copying the char buffer, copy the casted classes. I've left in a couple of `static_assert`s that I think both MSVC and GCC know how to handle. If the bots disagree with me, I'll remove them. - Check that the constructed type is either standard layout or a pointer. This protects against a programming error: we really want the "small" `DIEValue`s to be small and simple, so don't accidentally change them not to be. - Similarly, check that the size of the buffer is no bigger than a `uint64_t` or a pointer. (I thought checking against `sizeof(uint64_t)` would be good enough, but Chandler suggested that pointers might sometimes be bigger than that in the context of sanitizers.) I've also committed r238359 in the meantime, which introduces a DIEValue.def to simplify dispatching between the various types (thanks to a review comment by David Blaikie). Without that, this commit would be almost unintelligible. Here's the original commit message: -- Change `DIEValue` to be stored/passed/etc. by value, instead of reference. It's now a discriminated union, with a `Val` field storing the actual type. The classes that used to inherit from `DIEValue` no longer do. There are two categories of these: - Small values fit in a single pointer and are stored by value. - Large values require auxiliary storage, and are stored by reference. The only non-mechanical change is to tools/dsymutil/DwarfLinker.cpp. It was relying on `DIEInteger`s being passed around by reference, so I replaced that assumption with a `PatchLocation` type that stores a safe reference to where the `DIEInteger` lives instead. This commit causes a temporary regression in memory usage, since I've left merging `DIEAbbrevData` into `DIEValue` for a follow-up commit. I measured an increase from 845 MB to 879 MB, around 3.9%. The follow-up drops it lower than the starting point, and I've only recently brought the memory this low anyway, so I'm committing these changes separately to keep them incremental. (I also considered swapping the commits, but the other one first would cause a lot more code churn.) (I'm looking at `llc` memory usage on `verify-uselistorder.lto.opt.bc`; see r236629 for details.) -- llvm-svn: 238362
2015-05-28 06:14:58 +08:00
DIELoc *Loc = new (DIEValueAllocator) DIELoc;
DIEDwarfExpression DwarfExpr(*Asm, *this, *Loc);
const DIExpression *DIExpr = DV.getSingleExpression();
DwarfExpr.addFragmentOffset(DIExpr);
if (Location.isIndirect())
DwarfExpr.setMemoryLocationKind();
SmallVector<uint64_t, 8> Ops;
PR32382: Fix emitting complex DWARF expressions. The DWARF specification knows 3 kinds of non-empty simple location descriptions: 1. Register location descriptions - describe a variable in a register - consist of only a DW_OP_reg 2. Memory location descriptions - describe the address of a variable 3. Implicit location descriptions - describe the value of a variable - end with DW_OP_stack_value & friends The existing DwarfExpression code is pretty much ignorant of these restrictions. This used to not matter because we only emitted very short expressions that we happened to get right by accident. This patch makes DwarfExpression aware of the rules defined by the DWARF standard and now chooses the right kind of location description for each expression being emitted. This would have been an NFC commit (for the existing testsuite) if not for the way that clang describes captured block variables. Based on how the previous code in LLVM emitted locations, DW_OP_deref operations that should have come at the end of the expression are put at its beginning. Fixing this means changing the semantics of DIExpression, so this patch bumps the version number of DIExpression and implements a bitcode upgrade. There are two major changes in this patch: I had to fix the semantics of dbg.declare for describing function arguments. After this patch a dbg.declare always takes the *address* of a variable as the first argument, even if the argument is not an alloca. When lowering a DBG_VALUE, the decision of whether to emit a register location description or a memory location description depends on the MachineLocation — register machine locations may get promoted to memory locations based on their DIExpression. (Future) optimization passes that want to salvage implicit debug location for variables may do so by appending a DW_OP_stack_value. For example: DBG_VALUE, [RBP-8] --> DW_OP_fbreg -8 DBG_VALUE, RAX --> DW_OP_reg0 +0 DBG_VALUE, RAX, DIExpression(DW_OP_deref) --> DW_OP_reg0 +0 All testcases that were modified were regenerated from clang. I also added source-based testcases for each of these to the debuginfo-tests repository over the last week to make sure that no synchronized bugs slip in. The debuginfo-tests compile from source and run the debugger. https://bugs.llvm.org/show_bug.cgi?id=32382 <rdar://problem/31205000> Differential Revision: https://reviews.llvm.org/D31439 llvm-svn: 300522
2017-04-18 09:21:53 +08:00
if (Location.isIndirect() && Location.getOffset()) {
Ops.push_back(dwarf::DW_OP_plus);
Ops.push_back(Location.getOffset());
}
Ops.append(DIExpr->elements_begin(), DIExpr->elements_end());
DIExpressionCursor Cursor(Ops);
const TargetRegisterInfo &TRI = *Asm->MF->getSubtarget().getRegisterInfo();
if (!DwarfExpr.addMachineRegExpression(TRI, Cursor, Location.getReg()))
return;
DwarfExpr.addExpression(std::move(Cursor));
// Now attach the location information to the DIE.
addBlock(Die, Attribute, DwarfExpr.finalize());
}
/// Add a Dwarf loclistptr attribute data and value.
void DwarfCompileUnit::addLocationList(DIE &Die, dwarf::Attribute Attribute,
unsigned Index) {
dwarf::Form Form = DD->getDwarfVersion() >= 4 ? dwarf::DW_FORM_sec_offset
: dwarf::DW_FORM_data4;
Die.addValue(DIEValueAllocator, Attribute, Form, DIELocList(Index));
}
void DwarfCompileUnit::applyVariableAttributes(const DbgVariable &Var,
DIE &VariableDie) {
StringRef Name = Var.getName();
if (!Name.empty())
addString(VariableDie, dwarf::DW_AT_name, Name);
const auto *DIVar = Var.getVariable();
if (DIVar)
if (uint32_t AlignInBytes = DIVar->getAlignInBytes())
addUInt(VariableDie, dwarf::DW_AT_alignment, dwarf::DW_FORM_udata,
AlignInBytes);
addSourceLine(VariableDie, DIVar);
addType(VariableDie, Var.getType());
if (Var.isArtificial())
addFlag(VariableDie, dwarf::DW_AT_artificial);
}
/// Add a Dwarf expression attribute data and value.
void DwarfCompileUnit::addExpr(DIELoc &Die, dwarf::Form Form,
const MCExpr *Expr) {
Die.addValue(DIEValueAllocator, (dwarf::Attribute)0, Form, DIEExpr(Expr));
}
void DwarfCompileUnit::applySubprogramAttributesToDefinition(
const DISubprogram *SP, DIE &SPDie) {
auto *SPDecl = SP->getDeclaration();
auto *Context = resolve(SPDecl ? SPDecl->getScope() : SP->getScope());
applySubprogramAttributes(SP, SPDie, includeMinimalInlineScopes());
addGlobalName(SP->getName(), SPDie, Context);
}
bool DwarfCompileUnit::isDwoUnit() const {
return DD->useSplitDwarf() && Skeleton;
}
bool DwarfCompileUnit::includeMinimalInlineScopes() const {
return getCUNode()->getEmissionKind() == DICompileUnit::LineTablesOnly ||
(DD->useSplitDwarf() && !Skeleton);
}
} // end llvm namespace